{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PSKNJA3ONJ6XCNCLIYIPFBYWTT","short_pith_number":"pith:PSKNJA3O","canonical_record":{"source":{"id":"1905.12615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T17:57:23Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"8811ec64b1d87946fc3ae8f368eaae526d8974ed295f8580f38543954ec70747","abstract_canon_sha256":"46f1e41bd390d751548d519b78ade71e41c2e60a68a0cc91ab959b0cf1fc58d4"},"schema_version":"1.0"},"canonical_sha256":"7c94d4836e6a7d71344b4610f287169cf596a919ea7aaa942ae24faf2f08dc98","source":{"kind":"arxiv","id":"1905.12615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12615","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12615v1","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12615","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"PSKNJA3ONJ6X","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PSKNJA3ONJ6XCNCL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PSKNJA3O","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PSKNJA3ONJ6XCNCLIYIPFBYWTT","target":"record","payload":{"canonical_record":{"source":{"id":"1905.12615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T17:57:23Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"8811ec64b1d87946fc3ae8f368eaae526d8974ed295f8580f38543954ec70747","abstract_canon_sha256":"46f1e41bd390d751548d519b78ade71e41c2e60a68a0cc91ab959b0cf1fc58d4"},"schema_version":"1.0"},"canonical_sha256":"7c94d4836e6a7d71344b4610f287169cf596a919ea7aaa942ae24faf2f08dc98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:43.814813Z","signature_b64":"EZh+Lw4FTq+KmHJXNZToqZCVl/2Pqkxv+pQ4e/fC4QtZ3QwiimoXAg/E5lGvV85Q4pdEvAX8FD8UU8EnOZaVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c94d4836e6a7d71344b4610f287169cf596a919ea7aaa942ae24faf2f08dc98","last_reissued_at":"2026-05-17T23:44:43.814211Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:43.814211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.12615","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8LFa8daBErOuLcWK2dhO5nbcDkrfP4CAvsbijDPdzuSzs0HhvhbXocFTdAwZFs1d6ZBxxR/UP5sAzhsNo0DIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:02:50.299167Z"},"content_sha256":"76d3b69446ce99c20938e78dfd15e34b2a1c84e06f8b30c760923ee72f8c2473","schema_version":"1.0","event_id":"sha256:76d3b69446ce99c20938e78dfd15e34b2a1c84e06f8b30c760923ee72f8c2473"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PSKNJA3ONJ6XCNCLIYIPFBYWTT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Felicia Gao, Pan Xu, Quanquan Gu","submitted_at":"2019-05-29T17:57:23Z","abstract_excerpt":"We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $\\epsilon$-approximate stationary point of the performance function within $O(1/\\epsilon^{5/3})$ trajectories. This sample complexity improves upon the best known result $O(1/\\epsilon^2)$ by a factor of $O(1/\\epsilon^{1/3})$. At the core of our analysis is (i) a tighter upper bound for the variance of importance sampling weights, where we prove that the variance can be controlled "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12615","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"apaaLo5TWRbCKHuHykFnSVD7Zz0CCsQL/SDiE3oNpQgLJ/+zLxfVRbm/Fjnv0+Ijc/1C3OdKyoJrDHVICyRdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:02:50.299648Z"},"content_sha256":"f74bd74bd8ef432fb02fe0f17a9730f0cac52580e3482e8aa4ec5b8ac79842ae","schema_version":"1.0","event_id":"sha256:f74bd74bd8ef432fb02fe0f17a9730f0cac52580e3482e8aa4ec5b8ac79842ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/bundle.json","state_url":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T21:02:50Z","links":{"resolver":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT","bundle":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/bundle.json","state":"https://pith.science/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PSKNJA3ONJ6XCNCLIYIPFBYWTT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PSKNJA3ONJ6XCNCLIYIPFBYWTT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"46f1e41bd390d751548d519b78ade71e41c2e60a68a0cc91ab959b0cf1fc58d4","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T17:57:23Z","title_canon_sha256":"8811ec64b1d87946fc3ae8f368eaae526d8974ed295f8580f38543954ec70747"},"schema_version":"1.0","source":{"id":"1905.12615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12615","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12615v1","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12615","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"PSKNJA3ONJ6X","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PSKNJA3ONJ6XCNCL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PSKNJA3O","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:f74bd74bd8ef432fb02fe0f17a9730f0cac52580e3482e8aa4ec5b8ac79842ae","target":"graph","created_at":"2026-05-17T23:44:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $\\epsilon$-approximate stationary point of the performance function within $O(1/\\epsilon^{5/3})$ trajectories. This sample complexity improves upon the best known result $O(1/\\epsilon^2)$ by a factor of $O(1/\\epsilon^{1/3})$. At the core of our analysis is (i) a tighter upper bound for the variance of importance sampling weights, where we prove that the variance can be controlled ","authors_text":"Felicia Gao, Pan Xu, Quanquan Gu","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T17:57:23Z","title":"An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12615","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:76d3b69446ce99c20938e78dfd15e34b2a1c84e06f8b30c760923ee72f8c2473","target":"record","created_at":"2026-05-17T23:44:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"46f1e41bd390d751548d519b78ade71e41c2e60a68a0cc91ab959b0cf1fc58d4","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T17:57:23Z","title_canon_sha256":"8811ec64b1d87946fc3ae8f368eaae526d8974ed295f8580f38543954ec70747"},"schema_version":"1.0","source":{"id":"1905.12615","kind":"arxiv","version":1}},"canonical_sha256":"7c94d4836e6a7d71344b4610f287169cf596a919ea7aaa942ae24faf2f08dc98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c94d4836e6a7d71344b4610f287169cf596a919ea7aaa942ae24faf2f08dc98","first_computed_at":"2026-05-17T23:44:43.814211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:43.814211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EZh+Lw4FTq+KmHJXNZToqZCVl/2Pqkxv+pQ4e/fC4QtZ3QwiimoXAg/E5lGvV85Q4pdEvAX8FD8UU8EnOZaVBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:43.814813Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76d3b69446ce99c20938e78dfd15e34b2a1c84e06f8b30c760923ee72f8c2473","sha256:f74bd74bd8ef432fb02fe0f17a9730f0cac52580e3482e8aa4ec5b8ac79842ae"],"state_sha256":"524d93fced1021faadd9dac27a12c46b8cda88a6ef14fbcf34172e35bf53f3df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Dd5Zx3p2awb7NKrBWb4KGNsxe1vjMPa77z4x63qrbvpVRHvGTT+htY8oaLPjublCrfteKO90hAd572G8EbWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T21:02:50.302692Z","bundle_sha256":"d3083387da353d0c9c7a822525f5c4307461388f26abdd9637942cbfa73c7204"}}